Skip to content

MMSegmentation v0.18.0 Release
Compare
Choose a tag to compare
@Junjun2016 Junjun2016 released this 07 Oct 09:41
· 320 commits to master since this release
v0.18.0
8d49dd3
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Highlights

  • Support three real-time segmentation models (ICNet #884, BiSeNetV1 #851, and BiSeNetV2 #804)
  • Support one efficient segmentation model (FastFCN #885)
  • Support one efficient non-local/self-attention based segmentation model (ISANet #70)
  • Support COCO-Stuff 10k and 164k datasets (#625)
  • Support evaluate concated dataset separately (#833)
  • Support loading GT for evaluation from multi-file backend (#867)

New Features

  • Support three real-time segmentation models (ICNet #884, BiSeNetV1 #851, and BiSeNetV2 #804)
  • Support one efficient segmentation model (FastFCN #885)
  • Support one efficient non-local/self-attention based segmentation model (ISANet #70)
  • Support COCO-Stuff 10k and 164k datasets (#625)
  • Support evaluate concated dataset separately (#833)

Improvements

  • Support loading GT for evaluation from multi-file backend (#867)
  • Auto-convert SyncBN to BN when training on DP automatly(#772)
  • Refactor Swin-Transformer (#800)

Bug Fixes

  • Update mmcv installation in dockerfile (#860)
  • Fix number of iteration bug when resuming checkpoint in distributed train (#866)
  • Fix parsing parse in val_step (#906)
Assets 2